From: Catherine Hoang <catherine.hoang@oracle.com>
To: linux-xfs@vger.kernel.org
Subject: [PATCH 6.6 CANDIDATE v2 07/21] xfs: make sure maxlen is still congruent with prod when rounding down
Date: Mon, 5 Feb 2024 14:19:57 -0800 [thread overview]
Message-ID: <20240205222011.95476-8-catherine.hoang@oracle.com> (raw)
In-Reply-To: <20240205222011.95476-1-catherine.hoang@oracle.com>
From: "Darrick J. Wong" <djwong@kernel.org>
commit f6a2dae2a1f52ea23f649c02615d073beba4cc35 upstream.
In commit 2a6ca4baed62, we tried to fix an overflow problem in the
realtime allocator that was caused by an overly large maxlen value
causing xfs_rtcheck_range to run off the end of the realtime bitmap.
Unfortunately, there is a subtle bug here -- maxlen (and minlen) both
have to be aligned with @prod, but @prod can be larger than 1 if the
user has set an extent size hint on the file, and that extent size hint
is larger than the realtime extent size.
If the rt free space extents are not aligned to this file's extszhint
because other files without extent size hints allocated space (or the
number of rt extents is similarly not aligned), then it's possible that
maxlen after clamping to sb_rextents will no longer be aligned to prod.
The allocation will succeed just fine, but we still trip the assertion.
Fix the problem by reducing maxlen by any misalignment with prod. While
we're at it, split the assertions into two so that we can tell which
value had the bad alignment.
Fixes: 2a6ca4baed62 ("xfs: make sure the rt allocator doesn't run off the end")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
---
fs/xfs/xfs_rtalloc.c | 31 ++++++++++++++++++++++++++-----
1 file changed, 26 insertions(+), 5 deletions(-)
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 31fd65b3aaa9..0e4e2df08aed 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -211,6 +211,23 @@ xfs_rtallocate_range(
return error;
}
+/*
+ * Make sure we don't run off the end of the rt volume. Be careful that
+ * adjusting maxlen downwards doesn't cause us to fail the alignment checks.
+ */
+static inline xfs_extlen_t
+xfs_rtallocate_clamp_len(
+ struct xfs_mount *mp,
+ xfs_rtblock_t startrtx,
+ xfs_extlen_t rtxlen,
+ xfs_extlen_t prod)
+{
+ xfs_extlen_t ret;
+
+ ret = min(mp->m_sb.sb_rextents, startrtx + rtxlen) - startrtx;
+ return rounddown(ret, prod);
+}
+
/*
* Attempt to allocate an extent minlen<=len<=maxlen starting from
* bitmap block bbno. If we don't get maxlen then use prod to trim
@@ -248,7 +265,7 @@ xfs_rtallocate_extent_block(
i <= end;
i++) {
/* Make sure we don't scan off the end of the rt volume. */
- maxlen = min(mp->m_sb.sb_rextents, i + maxlen) - i;
+ maxlen = xfs_rtallocate_clamp_len(mp, i, maxlen, prod);
/*
* See if there's a free extent of maxlen starting at i.
@@ -355,7 +372,8 @@ xfs_rtallocate_extent_exact(
int isfree; /* extent is free */
xfs_rtblock_t next; /* next block to try (dummy) */
- ASSERT(minlen % prod == 0 && maxlen % prod == 0);
+ ASSERT(minlen % prod == 0);
+ ASSERT(maxlen % prod == 0);
/*
* Check if the range in question (for maxlen) is free.
*/
@@ -438,7 +456,9 @@ xfs_rtallocate_extent_near(
xfs_rtblock_t n; /* next block to try */
xfs_rtblock_t r; /* result block */
- ASSERT(minlen % prod == 0 && maxlen % prod == 0);
+ ASSERT(minlen % prod == 0);
+ ASSERT(maxlen % prod == 0);
+
/*
* If the block number given is off the end, silently set it to
* the last block.
@@ -447,7 +467,7 @@ xfs_rtallocate_extent_near(
bno = mp->m_sb.sb_rextents - 1;
/* Make sure we don't run off the end of the rt volume. */
- maxlen = min(mp->m_sb.sb_rextents, bno + maxlen) - bno;
+ maxlen = xfs_rtallocate_clamp_len(mp, bno, maxlen, prod);
if (maxlen < minlen) {
*rtblock = NULLRTBLOCK;
return 0;
@@ -638,7 +658,8 @@ xfs_rtallocate_extent_size(
xfs_rtblock_t r; /* result block number */
xfs_suminfo_t sum; /* summary information for extents */
- ASSERT(minlen % prod == 0 && maxlen % prod == 0);
+ ASSERT(minlen % prod == 0);
+ ASSERT(maxlen % prod == 0);
ASSERT(maxlen != 0);
/*
--
2.39.3
next prev parent reply other threads:[~2024-02-05 22:20 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-05 22:19 [PATCH 6.6 CANDIDATE v2 00/21] xfs backports for 6.6.y (from v6.7) Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 01/21] MAINTAINERS: add Catherine as xfs maintainer for 6.6.y Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 02/21] xfs: bump max fsgeom struct version Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 03/21] xfs: hoist freeing of rt data fork extent mappings Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 04/21] xfs: prevent rt growfs when quota is enabled Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 05/21] xfs: rt stubs should return negative errnos when rt disabled Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 06/21] xfs: fix units conversion error in xfs_bmap_del_extent_delay Catherine Hoang
2024-02-05 22:19 ` Catherine Hoang [this message]
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 08/21] xfs: introduce protection for drop nlink Catherine Hoang
2024-02-05 22:19 ` [PATCH 6.6 CANDIDATE v2 09/21] xfs: handle nimaps=0 from xfs_bmapi_write in xfs_alloc_file_space Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 10/21] xfs: allow read IO and FICLONE to run concurrently Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 11/21] xfs: factor out xfs_defer_pending_abort Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 12/21] xfs: abort intent items when recovery intents fail Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 13/21] xfs: only remap the written blocks in xfs_reflink_end_cow_extent Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 14/21] xfs: up(ic_sema) if flushing data device fails Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 15/21] xfs: fix internal error from AGFL exhaustion Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 16/21] xfs: fix again select in kconfig XFS_ONLINE_SCRUB_STATS Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 17/21] xfs: inode recovery does not validate the recovered inode Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 18/21] xfs: clean up dqblk extraction Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 19/21] xfs: dquot recovery does not validate the recovered dquot Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 20/21] xfs: clean up FS_XFLAG_REALTIME handling in xfs_ioctl_setattr_xflags Catherine Hoang
2024-02-05 22:20 ` [PATCH 6.6 CANDIDATE v2 21/21] xfs: respect the stable writes flag on the RT device Catherine Hoang
2024-02-06 5:23 ` [PATCH 6.6 CANDIDATE v2 00/21] xfs backports for 6.6.y (from v6.7) Chandan Babu R
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240205222011.95476-8-catherine.hoang@oracle.com \
--to=catherine.hoang@oracle.com \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox